Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17130
    Prev
    Next
    INDEX
    Explanations

    high-fat foods or references to fat content

    oai_token-act-pair · gpt-3.5-turbo

    references to fat content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schr
    -0.79
    SPONSORED
    -0.75
     Paran
    -0.73
     Historic
    -0.72
    HCR
    -0.71
     Dayton
    -0.69
    VILLE
    -0.68
     Curious
    -0.68
    Sensor
    -0.67
     Atlantis
    -0.67
    POSITIVE LOGITS
     fat
    1.09
    fat
    1.04
    rition
    0.97
    igue
    0.94
    asted
    0.93
    ohydrate
    0.88
    wallet
    0.85
    bag
    0.85
    tailed
    0.84
    rito
    0.82
    Activations Density 0.008%

    No Known Activations